Chat on AlpacaEval LC 2
84.3LC Win RateQwen 3 VL 32B Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen 3 VL 32B InstructParameters=32B2025.12 | 84.3 | |
| Qwen 2.5 32BParameters=32B2025.12 | 81.9 | |
| Olmo 3.1 32B InstructStage=DPO2025.12 | 69.7 | |
| Qwen 3 32BThinking=No, Parameters=32B2025.12 | 67.9 | |
| Gemma 3 27BParameters=27B2025.12 | 65.5 | |
| Olmo 3.1 32B InstructStage=Final Instruct 3.12025.12 | 59.8 | |
| Olmo 3.1 32B InstructStage=SFT2025.12 | 42.2 | |
| Gemma 2 27BParameters=27B2025.12 | 39.8 | |
| OLMo 2 32BParameters=32B2025.12 | 38 | |
| Qwen2.5-3B-GRLOBackbone=Qwen2.5-3B, Training Protocol=GRLO2026.05 | 35.7 | |
| Qwen2.5-3B-GRLO+RLVRBackbone=Qwen2.5-3B, Training Protocol=GRLO+RLVR2026.05 | 29.8 | |
| Qwen2.5-3B-InstructBackbone=Qwen2.5-3B, Training Protocol=Instruct2026.05 | 24.2 | |
| Apertus 70BParameters=70B2025.12 | 19.9 | |
| Qwen2.5-3B-RLVRBackbone=Qwen2.5-3B, Training Protocol=RLVR2026.05 | 12.3 | |
| Qwen2.5-3B-MathSFTBackbone=Qwen2.5-3B, Training Protocol=MathSFT2026.05 | 8.4 | |
| Qwen2.5-3B-BaseBackbone=Qwen2.5-3B, Training Protocol=Base2026.05 | 6.1 |